refactor: rag storage refactor (#2434)

This commit is contained in:
Aries-ckt
2025-03-17 14:15:21 +08:00
committed by GitHub
parent 34d86d693c
commit fc3fe6b725
52 changed files with 1134 additions and 797 deletions

View File

@@ -0,0 +1,45 @@
# BM25 RAG
In this example, we will show how to use the Elasticsearch as in DB-GPT RAG Storage. Using a Elasticsearch database to implement RAG can, to some extent, alleviate the uncertainty and interpretability issues brought about by Elasticsearch database retrieval.
### Install Dependencies
First, you need to install the `dbgpt elasticsearch storage` library.
```bash
uv sync --all-packages --frozen \
--extra "base" \
--extra "proxy_openai" \
--extra "rag" \
--extra "storage_elasticsearch" \
--extra "dbgpts"
````
### Prepare Elasticsearch
Prepare Elasticsearch database service, reference-[Elasticsearch Installation](https://www.elastic.co/guide/en/elasticsearch/reference/current/install-elasticsearch.html) .
### Elasticsearch Configuration
Set rag storage variables below in `configs/dbgpt-bm25-rag.toml` file, let DB-GPT know how to connect to Elasticsearch.
```
[rag.storage]
[rag.storage.full_text]
type = "ElasticSearch"
uri = "127.0.0.1"
port = "9200"
```
Then run the following command to start the webserver:
```bash
uv run python packages/dbgpt-app/src/dbgpt_app/dbgpt_server.py --config configs/dbgpt-bm25-rag.toml
```
Optionally
```bash
uv run python packages/dbgpt-app/src/dbgpt_app/dbgpt_server.py --config configs/dbgpt-bm25-rag.toml
```

View File

@@ -107,6 +107,10 @@ const sidebars = {
type: "doc",
id: "installation/integrations/oceanbase_rag_install"
},
{
type: "doc",
id: "installation/integrations/bm25_rag_install"
},
{
type: "doc",
id: "installation/integrations/milvus_rag_install"